Balancing ethics and statistics: machine learning facilitates highly accurate classification of mice according to their trait anxiety with reduced sample sizes

Abstract Understanding how individual differences influence vulnerability to disease and responses to pharmacological treatments represents one of the main challenges in behavioral neuroscience. Nevertheless, inter-individual variability and sex-specific patterns have been long disregarded in precli...

Full description

Saved in:
Bibliographic Details
Main Authors: Johannes Miedema, Beat Lutz, Susanne Gerber, Irina Kovlyagina, Hristo Todorov
Format: Article
Language:English
Published: Nature Publishing Group 2025-08-01
Series:Translational Psychiatry
Online Access:https://doi.org/10.1038/s41398-025-03546-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849225917581230080
author Johannes Miedema
Beat Lutz
Susanne Gerber
Irina Kovlyagina
Hristo Todorov
author_facet Johannes Miedema
Beat Lutz
Susanne Gerber
Irina Kovlyagina
Hristo Todorov
author_sort Johannes Miedema
collection DOAJ
description Abstract Understanding how individual differences influence vulnerability to disease and responses to pharmacological treatments represents one of the main challenges in behavioral neuroscience. Nevertheless, inter-individual variability and sex-specific patterns have been long disregarded in preclinical studies of anxiety and stress disorders. Recently, we established a model of trait anxiety that leverages the heterogeneity of freezing responses following auditory aversive conditioning to cluster female and male mice into sustained and phasic endophenotypes. However, unsupervised clustering required larger sample sizes for robust results which is contradictory to animal welfare principles. Here, we pooled data from 470 animals to train and validate supervised machine learning (ML) models for classifying mice into sustained and phasic responders in a sex-specific manner. We observed high accuracy and generalizability of our predictive models to independent animal batches. In contrast to data-driven clustering, the performance of ML classifiers remained unaffected by sample size and modifications to the conditioning protocol. Therefore, ML-assisted techniques not only enhance robustness and replicability of behavioral phenotyping results but also promote the principle of reducing animal numbers in future studies.
format Article
id doaj-art-78a820589d9e46e9ad1eba383ea4e5c9
institution Kabale University
issn 2158-3188
language English
publishDate 2025-08-01
publisher Nature Publishing Group
record_format Article
series Translational Psychiatry
spelling doaj-art-78a820589d9e46e9ad1eba383ea4e5c92025-08-24T11:51:37ZengNature Publishing GroupTranslational Psychiatry2158-31882025-08-0115111110.1038/s41398-025-03546-6Balancing ethics and statistics: machine learning facilitates highly accurate classification of mice according to their trait anxiety with reduced sample sizesJohannes Miedema0Beat Lutz1Susanne Gerber2Irina Kovlyagina3Hristo Todorov4Institute of Human Genetics, University Medical Center of the Johannes Gutenberg University MainzInstitute of Physiological Chemistry, University Medical Center of the Johannes Gutenberg University MainzInstitute of Human Genetics, University Medical Center of the Johannes Gutenberg University MainzInstitute of Physiological Chemistry, University Medical Center of the Johannes Gutenberg University MainzInstitute of Immunology, University Medical Center of the Johannes Gutenberg University MainzAbstract Understanding how individual differences influence vulnerability to disease and responses to pharmacological treatments represents one of the main challenges in behavioral neuroscience. Nevertheless, inter-individual variability and sex-specific patterns have been long disregarded in preclinical studies of anxiety and stress disorders. Recently, we established a model of trait anxiety that leverages the heterogeneity of freezing responses following auditory aversive conditioning to cluster female and male mice into sustained and phasic endophenotypes. However, unsupervised clustering required larger sample sizes for robust results which is contradictory to animal welfare principles. Here, we pooled data from 470 animals to train and validate supervised machine learning (ML) models for classifying mice into sustained and phasic responders in a sex-specific manner. We observed high accuracy and generalizability of our predictive models to independent animal batches. In contrast to data-driven clustering, the performance of ML classifiers remained unaffected by sample size and modifications to the conditioning protocol. Therefore, ML-assisted techniques not only enhance robustness and replicability of behavioral phenotyping results but also promote the principle of reducing animal numbers in future studies.https://doi.org/10.1038/s41398-025-03546-6
spellingShingle Johannes Miedema
Beat Lutz
Susanne Gerber
Irina Kovlyagina
Hristo Todorov
Balancing ethics and statistics: machine learning facilitates highly accurate classification of mice according to their trait anxiety with reduced sample sizes
Translational Psychiatry
title Balancing ethics and statistics: machine learning facilitates highly accurate classification of mice according to their trait anxiety with reduced sample sizes
title_full Balancing ethics and statistics: machine learning facilitates highly accurate classification of mice according to their trait anxiety with reduced sample sizes
title_fullStr Balancing ethics and statistics: machine learning facilitates highly accurate classification of mice according to their trait anxiety with reduced sample sizes
title_full_unstemmed Balancing ethics and statistics: machine learning facilitates highly accurate classification of mice according to their trait anxiety with reduced sample sizes
title_short Balancing ethics and statistics: machine learning facilitates highly accurate classification of mice according to their trait anxiety with reduced sample sizes
title_sort balancing ethics and statistics machine learning facilitates highly accurate classification of mice according to their trait anxiety with reduced sample sizes
url https://doi.org/10.1038/s41398-025-03546-6
work_keys_str_mv AT johannesmiedema balancingethicsandstatisticsmachinelearningfacilitateshighlyaccurateclassificationofmiceaccordingtotheirtraitanxietywithreducedsamplesizes
AT beatlutz balancingethicsandstatisticsmachinelearningfacilitateshighlyaccurateclassificationofmiceaccordingtotheirtraitanxietywithreducedsamplesizes
AT susannegerber balancingethicsandstatisticsmachinelearningfacilitateshighlyaccurateclassificationofmiceaccordingtotheirtraitanxietywithreducedsamplesizes
AT irinakovlyagina balancingethicsandstatisticsmachinelearningfacilitateshighlyaccurateclassificationofmiceaccordingtotheirtraitanxietywithreducedsamplesizes
AT hristotodorov balancingethicsandstatisticsmachinelearningfacilitateshighlyaccurateclassificationofmiceaccordingtotheirtraitanxietywithreducedsamplesizes